DeepMount00
/

Mistral-RAG

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

DeepMount00 commited on Apr 21, 2024

Commit

dc38c29

·

verified ·

1 Parent(s): 7c90f7a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ def generate_answer(prompt, response_type="generativo"):
     model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
     generated_ids = model.generate(model_inputs, max_new_tokens=200, do_sample=True,
                                    temperature=0.001, eos_token_id=tokenizer.eos_token_id)
-    decoded = tokenizer.batch_decode(generated_ids, skip_special_tokens=False)
     return decoded[0].split("[/INST]", 1)[1].strip() if "[/INST]" in decoded[0] else "Errore nella generazione della risposta"

     model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
     generated_ids = model.generate(model_inputs, max_new_tokens=200, do_sample=True,
                                    temperature=0.001, eos_token_id=tokenizer.eos_token_id)
+    decoded = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
     return decoded[0].split("[/INST]", 1)[1].strip() if "[/INST]" in decoded[0] else "Errore nella generazione della risposta"